Clik here to view.
Searching with bm25 does not return all results with GeoCoordinate filter
Could it be this issue? github.com/weaviate/weaviate Improvements to geo-coordinate based filtering opened 01:45PM - 19 Apr 24 UTC databyjp API design & UX data types Filtering / Sorting /...
View ArticleNot able to connect to weaviate instance from vectordbBench
I am trying to run vectorDBbench on weaviate for the performance run. (GitHub - zilliztech/VectorDBBench: A Benchmark Tool for VectorDB). Were you able to connect using the python client for example?...
View ArticleNot able to connect to weaviate instance from vectordbBench
Oh, I see. That code/benchmark is using our old client that doesn’t leverage the recent improvements over GRPC. It also targets our cloud, that should be instantiated first and with the proper...
View ArticleClik here to view.
Not able to connect to weaviate instance from vectordbBench
And by the way, if you want to learn about our take on benchmarking Weaviate, there are some nice contents here: weaviate.io Benchmarks | Weaviate You can find the following vector database...
View ArticleFeature request: auto delete collection
Adding something like pg_cron would allow this and more things. Detaching it from the DB puts data lifecycle demands on the application layer, which seems not directly tied. My problem is if I get an...
View ArticleSearching with bm25 does not return all results with GeoCoordinate filter
Yes, that very well could be the issue that I am seeing.
View ArticleClik here to view.
Full Metal Weaviate aka Weaviate for lazy people
Folks, This piece of soft kind of collapses graphql syntax layer and Weaviate syntax layer into something lean and convenient syntax-wise. You don’t have to care anymore about parenthesis or if you...
View ArticleNot able to connect to weaviate instance from vectordbBench
Thanks @DudaNogueira for replying.so , I have three questions here based on ur reply: whether the vectiordbBench benchmark code is compatible with latest weaviate code base? since u have mentioned "...
View Articleweaviate.exceptions.WeaviateQueryError: Query call with protocol GRPC search...
Description Hi, we’re using the Serverless Cloud tier and get the following exception(intermittently): weaviate.exceptions.WeaviateQueryError: Query call with protocol GRPC search failed with message...
View Article[Docs] Distance metrics incorrect range
I think the ranges for hamming and manhattan distance metrics are swapped here: Distance metrics | Weaviate. Hamming is 0..dims and manhattan is 0 .. Inf.
View ArticleLimit parameter change results of near_vector query
Description I’m geting an unexpected result running a near_vector search on my Weaviate database. The database contains 570 objects. Running a near vector query, using limit 3, I receive 3 wrong...
View ArticleClik here to view.
Limit parameter change results of near_vector query
@accorrea1-stf, Welcome to our community! It’s great to have you here. I wonder about the HNSW configuration in your cluster. Have you explored the ef operator? A higher ef value results in a more...
View ArticleLimit parameter change results of near_vector query
Thank you for your answer Mohamed! I’m going to do some tests increasing the ef value. Our current config is: {'cleanupIntervalSeconds': 300, 'distanceMetric': 'cosine', 'dynamicEfMin': 100,...
View ArticleOllama Embeddings call fails with wrong URL path: /api/embeddings
Description I’ve been struggling with getting Ollama and Weaviate (local hosted) to communicate and MAY have found an issue. Can someone confirm this?? Also, I run the client.py from a different...
View ArticleClik here to view.
Locally running RAG pipeline with Verba and Llama3 with Ollama
Thank you. I tried to use your docker compose file and got the following error: Gracefully stopping... (press Ctrl+C again to force) Error response from daemon: could not select device driver "nvidia"...
View ArticleText2vec ollama embedding error
I just stumbled on to this after making my own post. I think I’m seeing the same issue. Ollama API is listening on /api/embed not /api/embeddings/ Check out my post for context: Text2vec ollama...
View ArticleOllama Embeddings call fails with wrong URL path: /api/embeddings
Link to Ollama docs showing /api/embed: ollama/docs/api.md at main · ollama/ollama · GitHub Ah it has been superseded " Note: this endpoint has been superseded by /api/embed"
View ArticleNot able to connect to weaviate instance from vectordbBench
Hi @DudaNogueira, I tried running the solution u proposed from my local machine using python code. import weaviate client = weaviate.Client( url=“http://localhost:8080”,...
View ArticleLimit parameter change results of near_vector query
@accorrea1-stf Awesome, let me know how it goes.
View ArticleLocally running RAG pipeline with Verba and Llama3 with Ollama
Just checking, did you follow the instructions in the link posted “ollama dockerhub for GPU details”? Maybe you don’t have an Nvidia card or didn’t install the Nvidia Container Toolkit?
View Article